TradingAgents-astock
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment resea
What is TradingAgents-astock?
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。
Overview of TradingAgents-astock
What it is
TradingAgents-astock is a fork of the TradingAgents multi-agent investment research framework, specifically adapted for the A-share (Chinese stock) market. It is fully open-source under Apache 2.0, installable via pip with no external service dependencies. The project is intended for research and education purposes and does not constitute investment advice.
Key features
- 7 AI analyst roles: 4 original (Market, Social, News, Fundamentals) plus 3 A-share-specific (Policy Analyst, Hot Money Tracker, Lockup Monitor).
- All data sources are free and require no API keys: mootdx, Tencent Finance, East Money, Sina Finance, Flush, Cailianshe, Baidu Stock.
- A-share trading rule constraints: T+1, price limits, minimum lot sizes, ST stock handling.
- Dual LLM design: quick_think_llm for analysts/researchers/traders/risk debaters, deep_think_llm for research manager and portfolio manager.
- Output reports in Chinese (internal debate remains in English for reasoning quality).
- Benchmark is CSI 300 (instead of SPY).
Use cases
Multi-agent investment research for A-share stocks. Suitable for academic research, teaching, and experimental backtesting of AI-driven debate and decision-making in Chinese markets.
Getting started
bashgit clone https://github.com/simonlin1212/tradingagents-astock.gitcd tradingagents-astockpip install -e .After installation, configure your LLM API key in a .env file (see README for supported providers). Then run the Web UI with:bashstreamlit run web/app.pyOr use the CLI:bashtradingagents
License and pricing
Apache-2.0. Open source and free to use.
Based on the project's public README and repository metadata.
